{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,23]],"date-time":"2026-02-23T23:44:01Z","timestamp":1771890241265,"version":"3.50.1"},"reference-count":61,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"DOI":"10.13039\/501100003725","name":"National Research Foundation of Kore","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100003725","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003621","name":"Korea governmen","doi-asserted-by":"publisher","award":["NRF-2020R1A4A1019191"],"award-info":[{"award-number":["NRF-2020R1A4A1019191"]}],"id":[{"id":"10.13039\/501100003621","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2021]]},"DOI":"10.1109\/access.2021.3107548","type":"journal-article","created":{"date-parts":[[2021,8,24]],"date-time":"2021-08-24T20:13:43Z","timestamp":1629836023000},"page":"127068-127080","source":"Crossref","is-referenced-by-count":2,"title":["Deep Graph Fusion Based Multimodal Evoked Expressions From Large-Scale Videos"],"prefix":"10.1109","volume":"9","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7539-2016","authenticated-orcid":false,"given":"Ngoc-Huynh","family":"Ho","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3024-5060","authenticated-orcid":false,"given":"Hyung-Jeong","family":"Yang","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3575-5035","authenticated-orcid":false,"given":"Soo-Hyung","family":"Kim","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8756-1382","authenticated-orcid":false,"given":"Gueesang","family":"Lee","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6528-701X","authenticated-orcid":false,"given":"Seok-Bong","family":"Yoo","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref39","article-title":"Bridging the gap between spectral and spatial domains in graph neural networks","author":"balcilar","year":"2020","journal-title":"arXiv 2003 11702"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2012.2235192"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref32","first-page":"1","article-title":"Inception-v4, inception-ResNet and the impact of residual connections on learning","volume":"31","author":"szegedy","year":"2017","journal-title":"Proc AAAI Conf Artif Intell"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.308"},{"key":"ref30","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","author":"devlin","year":"2018","journal-title":"arXiv 1810 04805"},{"key":"ref37","author":"chung","year":"1997","journal-title":"Spectral Graph Theory"},{"key":"ref36","article-title":"Convolutional neural networks on graphs with fast localized spectral filtering","author":"defferrard","year":"2016","journal-title":"arXiv 1606 09375"},{"key":"ref35","article-title":"Spectral networks and locally connected networks on graphs","author":"bruna","year":"2013","journal-title":"arXiv 1312 6203"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/W14-4012"},{"key":"ref60","article-title":"Swin transformer: Hierarchical vision transformer using shifted windows","author":"liu","year":"2021","journal-title":"arXiv 2103 14030"},{"key":"ref61","article-title":"Neural machine translation by jointly learning to align and translate","author":"bahdanau","year":"2014","journal-title":"arXiv 1409 0473"},{"key":"ref28","article-title":"Inductive representation learning on large graphs","author":"hamilton","year":"2017","journal-title":"arXiv 1706 02216"},{"key":"ref27","article-title":"Semi-supervised classification with graph convolutional networks","author":"kipf","year":"2016","journal-title":"arXiv 1609 02907"},{"key":"ref29","first-page":"747","article-title":"Emotion understanding in videos through body, context, and visual-semantic embedding loss","author":"filntisis","year":"2020","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.15439\/2016F535"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.5220\/0006357903830389"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.2984368"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1016\/j.imu.2020.100424"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/WiSPNET.2017.8300161"},{"key":"ref24","article-title":"WaveNet: A generative model for raw audio","author":"van den oord","year":"2016","journal-title":"arXiv 1609 03499"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1016\/j.procs.2015.10.020"},{"key":"ref26","first-page":"1068","article-title":"Neural audio synthesis of musical notes with WaveNet autoencoders","author":"engel","year":"2017","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TENCON.2019.8929257"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2020.12.001"},{"key":"ref51","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"arXiv 1706 03762"},{"key":"ref59","article-title":"Less is more: Sparse sampling for dense reaction predictions","author":"lin","year":"2021","journal-title":"arXiv 2106 01764"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1994.6.2.181"},{"key":"ref57","article-title":"Learnable pooling with context gating for video classification","author":"miech","year":"2017","journal-title":"arXiv 1706 06905"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952261"},{"key":"ref55","first-page":"6105","article-title":"EfficientNet: Rethinking model scaling for convolutional neural networks","author":"tan","year":"2019","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1145\/3310195.3310201"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1186\/s13640-017-0194-1"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.324"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1016\/j.conb.2020.12.007"},{"key":"ref11","article-title":"DADgraph: A discourse-aware dialogue graph neural network for multiparty dialogue machine reading comprehension","author":"li","year":"2021","journal-title":"arXiv 2104 12377"},{"key":"ref40","article-title":"Geometric deep learning on graphs and manifolds using mixture model CNNs","author":"monti","year":"2016","journal-title":"arxiv 161108402"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1089\/big.2020.0274"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1037\/emo0000694"},{"key":"ref14","article-title":"A commonsense reasoning framework for explanatory emotion attribution, generation and re-classification","author":"lieto","year":"2021","journal-title":"arXiv 2101 04017"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijhcs.2007.10.011"},{"key":"ref16","article-title":"EEV: A large-scale dataset for studying evoked expressions from video","author":"sun","year":"2021","journal-title":"arXiv 2001 05488"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2014.2305573"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298687"},{"key":"ref19","first-page":"1097","article-title":"ImageNet classification with deep convolutional neural networks","volume":"25","author":"krizhevsky","year":"2012","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.3390\/s21093046"},{"key":"ref3","first-page":"1","article-title":"Improving emotion recognition is associated with subsequent mental health and wellbeing in children with severe behavioural problems","author":"wells","year":"2020","journal-title":"European Child & Adolescent Psychiatry"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2020.107694"},{"key":"ref5","first-page":"1","article-title":"Fusion of machine learning and privacy preserving for secure facial expression recognition","volume":"2021","author":"ullah","year":"2021","journal-title":"Secur Commun Netw"},{"key":"ref8","article-title":"MLT-DNet: Speech emotion recognition using 1D dilated CNN based on multi-learning trick approach","volume":"167","author":"kwon","year":"2021","journal-title":"Expert Syst Appl"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.3390\/s21041249"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472192"},{"key":"ref9","first-page":"1","article-title":"Towards estimating affective states in virtual reality based on behavioral data","author":"holzwarth","year":"2021","journal-title":"Virtual Reality"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/JBHI.2018.2824327"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N16-1020"},{"key":"ref48","article-title":"Speech enhancement using a deep mixture of experts","author":"chazan","year":"2017","journal-title":"arXiv 1703 09302"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682773"},{"key":"ref42","first-page":"1","article-title":"Efficient large-scale multi-modal classification","volume":"32","author":"kiela","year":"2018","journal-title":"Proc AAAI Conf Artif Intell"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2017.2738401"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-662-44415-3_16"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-24571-8_47"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/9312710\/09521910.pdf?arnumber=9521910","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,12,17]],"date-time":"2021-12-17T19:57:38Z","timestamp":1639771058000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9521910\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"references-count":61,"URL":"https:\/\/doi.org\/10.1109\/access.2021.3107548","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021]]}}}